Page - 61 - in Short-Term Load Forecasting by Artificial Intelligent Technologies

Energies2019,12, 164 Table6.DAYTOWN:Results for2015. Month ForecastModel MI+ANN Bi-Level MI+ANN+mEDE MAPE Variance MAPE Variance MAPE Variance January 3.86 1.92 3.27 1.36 1.25 1.03 February 3.85 1.71 2.30 1.47 1.20 0.99 March 3.80 1.75 2.20 1.44 1.22 1.05 April 3.71 1.79 2.24 1.38 1.27 1.06 May 3.79 1.87 2.28 1.40 1.22 1.02 June 3.72 1.85 2.13 1.30 1.24 1.07 July 3.76 1.76 2.22 1.36 1.28 0.99 August 3.87 1.76 2.18 1.43 1.26 1.08 September 3.70 2.70 2.29 1.38 1.23 1.02 October 3.77 1.88 2.17 1.36 1.21 1.09 November 3.83 1.83 2.27 1.50 1.27 1.00 December 3.80 1.81 2.25 1.33 1.21 1.01 Average 3.78 1.88 2.31 1.39 1.23 1.03 Table7.Comparisonof training iterations (convergence)andregressionanalysis (accuracy). Dataset ForecastModel Iterations Training Testing Validation MI+ANN 20 0.9626 0.9619 0.9556 DAYTOWN Bi-Level 94 0.9787 0.9799 0.9776 MI+ANN+mEDE 95 0.9876 0.9890 0.9872 MI+ANN 23 0.9622 0.9617 0.9551 EKPC Bi-Level 95 0.9769 0.9783 0.9766 MI+ANN+mEDE 96 0.9877 0.9892 0.9878 5.ConclusionsandFutureWork In SGs, DALF is an essential task because its accuracy has a direct impact on the planning schedulesofutilities that stronglyaffects theenergy trademarket.Moreover,highvolatility in the history loadcurvesmakesDALFinSGsrelativelymorechallengingwhencomparedto loadforecast for longerduration. TakingintoaccountDALFinfluencingfactorssuchasexogenousvariablesand meteorologicalvariables,wehavepresentedahybridANN-basedDALFmodel forSGswhich isa multi-model forecastingANNwithasupervisedarchitectureandMARAfor training. Theproposed model significantly reduced the execution time and enhanced the forecast accuracy bydistinctly carrying localnormalizationandlocal training.Moreover, sigmoidactivation functionandMARA enable the forecast strategytocapturenon-linearities in load-timeseries. Integrationofoptimization module (basedonourproposedmodifications)with the forecast strategyalso improvedthe forecast accuracy. TestsareconductedonthreeUSAgrids:DAYTOWN,EKPCandFE.Results showthat the proposedmodel achieves relativelybetter forecast accuracy (98.76%) in comparison toanexisting bi-leveltechniqueandanMI+ANNtechnique.Moreover, improvementinforecastaccuracyisachieved whilenotpaying the cost of slowconvergence rate. Thus, the trade-off betweenconvergence rate andforecast isnotcreated. Finally, fromapplicationperspective, theproposedmodelcanbeusedby utilities to launchbetteroffers intheelectricitymarket. Thismeansthat theutilitiescansavesignificant amountofmoneyduetobetteradjustmentof theirgenerationanddemandschedulessimplybecause ofhighaccuracyof theproposedmodel. In future,weare interested inadvancedsignalprocessingtechniques for featureselectionand extractionpurposes.Moreover,explorationofparticleswarmoptimization-basedtechniquesanda complete forecastplusscheduling-basedtechnique isalsounderconsideration. 61